Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add karellen/karellen-jdb-mcp --skill jdb-debuggit clone --depth 1 https://github.com/karellen/karellen-jdb-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/karellen/karellen-jdb-mcp/jdb-debug)<a href="https://agentmods.dev/skills/karellen/karellen-jdb-mcp/jdb-debug"><img src="https://agentmods.dev/badge/skills/karellen/karellen-jdb-mcp/jdb-debug/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/karellen/karellen-jdb-mcp/jdb-debug"><img src="https://agentmods.dev/badge/skills/karellen/karellen-jdb-mcp/jdb-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.02095 |
| Opus 5 | $0.00017 | $0.01047 |
| Sonnet 5 | $0.00007 | $0.00419 |
| Haiku 4.5 | $0.00003 | $0.00210 |
Grade A, and why
jdb-debug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JDB Debugging Workflow
Use this skill when the user wants to debug a Java application, investigate an exception, inspect runtime state, or understand execution flow.
Prerequisites
jdbmust be installed and on PATH (comes with the JDK)- The target JVM must be started with JDWP debug agent enabled (see below)
suspend=ypauses the JVM until the debugger attaches (recommended for startup debugging)suspend=nlets the JVM run immediately (for attaching to a live process)
Launching the JVM with Debug Support
You (Claude) will typically start the JVM yourself before connecting. The JDWP agent stanza
varies by launcher. Pick a free port (e.g. 5005) and use suspend=y so the JVM waits for
you to attach.
Plain java
java -agentlib:jdwp=transport=dt_socket,server=y,suspend=y,address=*:5005 \
-cp target/classes com.example.Main
Maven (Surefire / Failsafe tests)
mvn test -Dmaven.surefire.debug="-agentlib:jdwp=transport=dt_socket,server=y,suspend=y,address=*:5005"
Or the built-in shorthand (uses port 5005 by default):
mvn -Dmaven.surefire.debug test
For Failsafe integration tests replace surefire with failsafe.
Maven (application via exec-maven-plugin)
MAVEN_OPTS="-agentlib:jdwp=transport=dt_socket,server=y,suspend=y,address=*:5005" \
mvn exec:java -Dexec.mainClass=com.example.Main
Gradle (tests)
./gradlew test --debug-jvm # uses port 5005 by default, suspend=y
Gradle (application via JavaExec)
Add to the task or pass via env:
JAVA_OPTS="-agentlib:jdwp=transport=dt_socket,server=y,suspend=y,address=*:5005" \
./gradlew run
OSGi / Eclipse Tycho (Surefire)
Tycho Surefire uses the same property as Maven Surefire:
mvn verify -Dmaven.surefire.debug="-agentlib:jdwp=transport=dt_socket,server=y,suspend=y,address=*:5005"
Or with the tycho.testArgLine property:
mvn verify -Dtycho.testArgLine="-agentlib:jdwp=transport=dt_socket,server=y,suspend=y,address=*:5005"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 225 lines · 35 tokens per session scan A 7c61bf46f4fe
jdb-debug is a skill published in the GitHub repository karellen/karellen-jdb-mcp (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 2,095 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.
wxjava-troubleshooter
A troubleshooting guide for WxJava, a Java library used to connect applications to WeChat services. It organizes problems involving setup, access tokens, signatures, payment certificates, callbacks, data conversion, network requests, and multiple accounts.
performance-smell-detection
Detect potential code-level performance smells in Java - streams, collections, boxing, regex, object creation. Provides awareness, not absolutes - always measure before optimizing. For JPA/database performance, use jpa-patterns instead.
126-java-exception-handling
Use when you need to apply Java exception handling best practices — including using specific exception types, managing resources with try-with-resources, securing exception messages, preserving error context via exception chaining, validating inputs early with fail-fast principles, handling thread interruption…
jstall
This skill should be used when the user asks about "JVM performance", "Java thread dump", "Java deadlock", "JVM diagnosis", "what is my Java application doing", "slow Java", "Java profiling", "flamegraph", "Java CPU usage", "thread contention", "JVM inspection", "jstall", or any question about analyzing, debugging, or…
java-heap-dump-triage
A guide for investigating Java memory problems using heap dumps and related reports. A heap dump is a snapshot of objects held in the Java Virtual Machine's memory.